Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 270 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 8.8067. Min Range: -8.8067
Max Act: 8.8067. Min Act: -0.1700
Data Index: 5312388 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8067. Min Range: -8.8067
Max Act: 8.8067. Min Act: -0.1700
Data Index: 5694124 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8067. Min Range: -8.8067
Max Act: 8.8067. Min Act: -0.1700
Data Index: 3732324 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8067. Min Range: -8.8067
Max Act: 8.8067. Min Act: -0.1700
Data Index: 7615359 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8067. Min Range: -8.8067
Max Act: 8.8067. Min Act: -0.1700
Data Index: 2396591 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8067. Min Range: -8.8067
Max Act: 8.7442. Min Act: -0.1700
Data Index: 8734694 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8067. Min Range: -8.8067
Max Act: 8.6817. Min Act: -0.1700
Data Index: 8826194 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8067. Min Range: -8.8067
Max Act: 8.6817. Min Act: -0.1700
Data Index: 4176630 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8067. Min Range: -8.8067
Max Act: 8.5567. Min Act: -0.1700
Data Index: 2130078 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8067. Min Range: -8.8067
Max Act: 8.6192. Min Act: -0.1700
Data Index: 728430 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8067. Min Range: -8.8067
Max Act: 8.5567. Min Act: -0.1700
Data Index: 7118827 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8067. Min Range: -8.8067
Max Act: 8.6817. Min Act: -0.1700
Data Index: 688861 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8067. Min Range: -8.8067
Max Act: 8.6192. Min Act: -0.1699
Data Index: 7912536 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8067. Min Range: -8.8067
Max Act: 8.5567. Min Act: -0.1700
Data Index: 7952670 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8067. Min Range: -8.8067
Max Act: 8.4942. Min Act: -0.1700
Data Index: 5249145 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8067. Min Range: -8.8067
Max Act: 8.4942. Min Act: -0.1700
Data Index: 1478942 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8067. Min Range: -8.8067
Max Act: 8.4942. Min Act: -0.1700
Data Index: 4072729 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8067. Min Range: -8.8067
Max Act: 8.5567. Min Act: -0.1700
Data Index: 179777 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8067. Min Range: -8.8067
Max Act: 8.4942. Min Act: -0.1700
Data Index: 1407657 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8067. Min Range: -8.8067
Max Act: 8.4942. Min Act: -0.1700
Data Index: 6139950 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19